Mobility Management for TCP in mmWave Networks

Communication at millimeter wave (mmWave) frequencies will likely be a cornerstone for next generation 5G cellular networks. However, providing mobility support for end-to-end applications in mmWave cellular systems is challenging due to the relatively small coverage area of individual cells, and rapid channel dynamics caused by blockage and beam-tracking. This paper presents a comprehensive performance evaluation of TCP on top of mmWave cellular systems with mobility management, detailed modeling of the channel dynamics, and end-to-end network architectures. We show how an efficient mobility management scheme in a dense network deployment can dramatically improve the performance of TCP in terms of both throughput and latency in mobile scenarios with blocking. The study also reveals that, even with fast mobility management, TCP throughput is extremely sensitive to the end-to-end delay with implications on both core network and server location.

[1]  Sally Floyd,et al.  HighSpeed TCP for Large Congestion Windows , 2003, RFC.

[2]  Bogdan M. Wilamowski,et al.  The Transmission Control Protocol , 2005, The Industrial Information Technology Handbook.

[3]  Michele Zorzi,et al.  Performance Comparison of Dual Connectivity and Hard Handover for LTE-5G Tight Integration in mmWave Cellular Networks , 2016, ArXiv.

[4]  Rittwik Jana,et al.  TCP in 5G mmWave networks: Link level retransmissions and MP-TCP , 2017, 2017 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[5]  Ulas C. Kozat,et al.  A new control plane for 5G network architecture with a case study on unified handoff, mobility, and routing management , 2014, IEEE Communications Magazine.

[6]  Theodore S. Rappaport,et al.  Millimeter-Wave Cellular Wireless Networks: Potentials and Challenges , 2014, Proceedings of the IEEE.

[7]  Masaki Bandai,et al.  A transport protocol for millimeter-wave links , 2017 .

[8]  Donald F. Towsley,et al.  Models of TCP in high-BDP environments and their experimental validation , 2016, 2016 IEEE 24th International Conference on Network Protocols (ICNP).

[9]  Sundeep Rangan,et al.  Transport layer performance in 5G mmWave cellular , 2016, 2016 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[10]  Mikio Iwamura.  NGMN View on 5G Architecture , 2015, 2015 IEEE 81st Vehicular Technology Conference (VTC Spring).

[11]  Jing Zhu,et al.  The Bufferbloat Problem over Intermittent Multi-Gbps mmWave Links , 2016, ArXiv.

[12]  Gerhard Fettweis,et al.  Mobility Modeling and Performance Evaluation of Multi-Connectivity in 5G Intra-Frequency Networks , 2015, 2015 IEEE Globecom Workshops (GC Wkshps).

[13]  Matteo Drago,et al.  X-TCP: a cross layer approach for TCP uplink flows in mmwave networks , 2017, 2017 16th Annual Mediterranean Ad Hoc Networking Workshop (Med-Hoc-Net).

[14]  Sundeep Rangan,et al.  Improved Handover Through Dual Connectivity in 5G mmWave Mobile Networks , 2016, IEEE Journal on Selected Areas in Communications.

[15]  Daniela Tuninetti,et al.  Coverage in mmWave Cellular Networks With Base Station Co-Operation , 2015, IEEE Transactions on Wireless Communications.

[16]  Sneha Kumar Kasera,et al.  Towards understanding TCP performance on LTE/EPC mobile networks , 2014, AllThingsCellular '14.

[17]  Sundeep Rangan,et al.  ns-3 Implementation of the 3GPP MIMO Channel Model for Frequency Spectrum above 6 GHz , 2017, WNS3.

[18]  Sundeep Rangan,et al.  A Framework for End-to-End Evaluation of 5G mmWave Cellular Networks in ns-3 , 2016, WNS3 '16.

[19]  Åke Arvidsson,et al.  Behaviour of Common TCP Variants over LTE , 2016, 2016 IEEE Global Communications Conference (GLOBECOM).

[20]  Lili Wang,et al.  A Conservative Loss Recovery Algorithm Based on Selective Acknowledgment (SACK) for TCP , 2012, RFC.

[21]  J Gettys,et al.  Bufferbloat: Dark Buffers in the Internet , 2011, IEEE Internet Computing.

[22]  Junyi Li,et al.  Network densification: the dominant theme for wireless evolution into 5G , 2014, IEEE Communications Magazine.